Autotrain compatible Base model:finetune:meta-llama... Base model:meta-llama/llama-3.... Conversational Endpoints compatible Instruct Llama Region:us Safetensors Vi
Model Card on HF 🤗: https://huggingface.co/kiki-ailab/Llama3.2-1B-Instruct-KAI
Llama3.2 1B Instruct KAI Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Llama3.2 1B Instruct KAI Parameters and Internals
| LLM Name | Llama3.2 1B Instruct KAI |
| Repository 🤗 | https://huggingface.co/kiki-ailab/Llama3.2-1B-Instruct-KAI |
| Base Model(s) | |
| Model Size | 1b |
| Required VRAM | 2.5 GB |
| Updated | 2025-07-28 |
| Maintainer | kiki-ailab |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | vi |
| Model Architecture | LlamaForCausalLM |
| License | other |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.43.3 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|finetune_right_pad_id|> |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives to Llama3.2 1B Instruct KAI
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama 3.2 1B Instruct | 128K / 2.5 GB | 3333600 | 1011 |
| Llama 3.2 1B Instruct | 128K / 2.5 GB | 68523 | 76 |
| Llasa 1B Multilingual | 128K / 3.5 GB | 62811 | 38 |
| ...enchmaxx Llama 3.2 1B Instruct | 128K / 0 GB | 130 | 3 |
| MINT 1B | 128K / 2.5 GB | 101 | 0 |
| Nano Imp 1B | 128K / 3 GB | 901 | 20 |
| MiniThinky V2 1B Llama 3.2 | 128K / 4.9 GB | 3444 | 41 |
| BunderMaxx 1010 | 128K / 2.5 GB | 14 | 1 |
| Llama 3.2 1b OrcaSun V1 | 128K / 3 GB | 5 | 0 |
| Mini Think Base 1B | 128K / 2.5 GB | 60 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than kiki-ailab/Llama3.2-1B-Instruct-KAI .
Rank the Llama3.2 1B Instruct KAI Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 50200 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124